AI Resume Screener

The proposed AI Resume Screener successfully automates resume evaluation by integrating NLP, machine learning, and NVIDIA LLaMA 3.1. The system demonstrated measurable improvements in efficiency, reducing resume processing time to just a few seconds, while enhancing candidate-job match accuracy through semantic similarity analysis.   Features such as skill gap identification, ATS optimization, bias detection, and AI-powered summarization provided recruiters with deeper insights and ensured fairer, more transparent hiring decisions. The HR dashboard further improved usability by offering real-time analytics and candidate ranking, contributing to higher recruiter satisfaction. Overall, the system proved to be a reliable, scalable, and intelligent solution for modern recruitment challenges.   Looking ahead, several enhancements can extend the system’s capabilities. Multilingual support will allow screening of resumes across diverse languages, broadening applicability in global recruitment. Cloud scalability and integration with popular job portals will enable seamless deployment at enterprise scale.   Advanced predictive analytics could provide insights into candidate success rates, while mobile application support would make the system accessible on-the-go. Further improvements in bulk processing optimization and custom scoring algorithms will refine accuracy and efficiency. Finally, expanding ethical AI practices, including stronger bias mitigation and fairness auditing, will ensure the system continues to promote equitable hiring.  

[1]              NVIDIA, “Llama 3.1 Model Documentation. This reference describes the NVIDIA Llama 3.1 model, which is a powerful large language model used for advanced text understanding and generation. In this project, it is used for tasks such as resume summarization, generating hiring recommendations, and performing intelligent analysis. It enhances the system’s ability to understand context and provide human-like insights.   [2]              spaCy, “Natural Language Processing Library Documentation. spaCy is a widely used NLP library that helps in processing and analyzing text data. It is used in the project for extracting structured information from resumes, such as skills, education, and experience. spaCy performs tasks like tokenization, part-of-speech tagging, and named entity recognition, making resume data easier to analyze.   [3]              SentenceTransformers, “Semantic Similarity Models. SentenceTransformers is used to convert text into vector representations (embeddings) that capture meaning. In this system, it helps compare resumes with job descriptions using semantic similarity. This allows the system to match candidates based on meaning rather than exact keywords, improving accuracy.   [4]              FastAPI, “FastAPI Framework Documentation. FastAPI is a modern web framework used to build the backend of the system. It handles API requests, processes data, and connects different modules of the application. It is known for its high performance and speed, which helps the system deliver real-time results.   [5]              scikit-learn, “Machine Learning Toolkit Documentation. scikit-learn is a machine learning library used to implement algorithms such as Logistic Regression and Support Vector Machines (SVM). In this project, it is used for predicting the most suitable job role for a candidate based on their skills and experience.   [6]              PyMuPDF, “PDF Parsing Library Documentation.  PyMuPDF is a library used to extract text from PDF files. It helps in reading resume documents and converting them into raw text format. This is the first step in resume processing before applying NLP techniques.   [7]              pdfminer.six, “PDF Text Extraction Library. pdfminer.six is another tool used for extracting text from PDFs. It complements PyMuPDF by providing more detailed text extraction capabilities, especially for complex or structured documents. Together, they improve the accuracy of resume parsing.   [8]              Vaswani et al., “Attention is All You Need,” NeurIPS,        2017. This is a foundational research paper that introduced  the Transformer model, which is the basis of modern NLP systems like BERT and Llama. It explains how attention mechanisms help models understand relationships between words in a sentence, enabling better context understanding. [9]               Devlin et al., “BERT: Pre-training of Deep Bidirectional Transformers,” 2019. This paper introduces BERT, a powerful NLP model that understands text in both directions (left and right context). It significantly improved tasks like text classification and semantic understanding. Concepts from BERT are used in modern systems like SentenceTransformers for better text analysis. [10]            Sunny Ramchandani, Preksha Jain, Amey Shivhare,Maddu Akhil, Shashank Pandey, “AI Resume Analyzer: A Review and Case Study of an NLP-Driven Recruitment System,” International Journal of Science, Engineering and Technology, Vol. 13, Issue 5, 2025. This paper reviews the evolution of resume analysis approaches, from keywordbased filters to large language models (LLMs) and RetrievalAugmented Generation (RAG) pipelines. It compares accuracy, scalability, fairness, and compliance across methods, and presents a case study of an AI Resume Analyzer system with experimental validation. Ethical concerns such as bias and privacy are also discussed [11]            R. Muthu Kumar, “AI-Based Resume Analyzer Using NLP and Machine Learning,”  International Journal of Innovative Research in  Technology (IJIRT), Vol. 12, Issue 1, June 2025. This study proposes an AI-based resume analyzer that leverages NLP and ML to automate resume screening and job-role matching. The system extracts relevant information such as skills, education, and experience, then computes a match score against job descriptions. Developed using Python and React.js, it emphasizes bias-free, efficient, and transparent hiring